Path: utzoo!attcan!uunet!mcvax!unido!uklirb!xinzhi
From: xinzhi@uklirb.UUCP (Xinzhi Li AG Richter)
Newsgroups: comp.ai.neural-nets
Subject: When does a hopfield net converge ?
Message-ID: <6009@uklirb.UUCP>
Date: 10 Jul 89 15:43:16 GMT
Reply-To: xinzhi@uklirb.UUCP (Xinzhi Li AG Richter)
Organization: University of Kaiserslautern, W-Germany
Lines: 18

When does a hopfield net converge to stead state? If it
converges, how many steps will it take to enter the stead state? I
tried to answer such problems by using methods of linear algebra
(i.e. eigenvalue related methods).  I always got trouble with
the non-linearity caused by the threshold function. Does anyone knows
any method to overcome such difficulty? Does anyone knows any theorem in
this direction? 

I have read a assertion in a article of Lippmann (Apr. 1987 IEEE ASSP)
that a hopfield net could always converge given that the net is
symmetric and completely connected. But i can not get the proof of this
assertion. Does anyone knows the paper proving this assertion? Which
methods are used there?

Thank you in advance.
---------------------------------------------------
xinzhi@uklirb.uucp
Xinzhi Li, university kaiserslautern, west germany